Publications

An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision–Language Pretraining

Published in Nature Biomedical Engineering 2026, 2026

In this work, we present ConceptCLIP, an explainable biomedical foundation model pretrained on MedConcept-23M with joint image–text and region–concept alignment, enabling strong medical image understanding together with concept-level explanations across diverse imaging modalities.

Recommended citation: Yuxiang Nie*, Sunan He*, Yequan Bie*, Yihui Wang, Zhixuan Chen, Shu Yang, Zhiyuan Cai, Linshan Wu, Hongmei Wang, Xi Wang, Ngai Shing Cheng, Luyang Luo, Mingxiang Wu, Haibo Jin, Xian Wu, Ronald Cheong Kin Chan, Yuk Ming Lau, Zhengyu Zhang, Sushan Xiao, Can Yang, Yinghua Zhao, Xiaohui Duan, Li Zhang, Li Liang, Yefeng Zheng, Pranav Rajpurkar, and Hao Chen. 2026. An explainable biomedical foundation model via large-scale concept-enhanced vision–language pretraining. Nature Biomedical Engineering. https://doi.org/10.1038/s41551-026-01764-x. (* equal contribution) https://www.nature.com/articles/s41551-026-01764-x

Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration

Published in Nature Biomedical Engineering 2026, 2026

In this work, we propose Generalist-Specialist Collaboration (GSCo), a cooperative framework that combines a medical generalist foundation model with lightweight specialist models for more generalizable AI in medicine.

Recommended citation: Sunan He*, Yuxiang Nie*, Hongmei Wang, Shu Yang, Yihui Wang, Zhiyuan Cai, Zhixuan Chen, Yingxue Xu, Linshan Wu, Ngai Shing Cheng, Luyang Luo, Huiling Xiang, Xi Lin, Mingxiang Wu, Yifan Peng, George Shih, Ziyang Xu, Xian Wu, Qiong Wang, Ronald Cheong Kin Chan, Varut Vardhanabhuti, Xiaohui Duan, Winnie Chiu Wing Chu, Yefeng Zheng, Pranav Rajpurkar, Kang Zhang, and Hao Chen. 2026. Towards generalizable AI in medicine via Generalist-Specialist Collaboration. Nature Biomedical Engineering. https://doi.org/10.1038/s41551-026-01653-3. (* equal contribution) https://www.nature.com/articles/s41551-026-01653-3

Mix-Initiative Response Generation with Dynamic Prefix Tuning

Published in NAACL 2024, 2024

In this work, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model.

Recommended citation: Yuxiang Nie, Heyan Huang, Xian-Ling Mao, and Lizi Liao. 2024. Mix-Initiative Response Generation with Dynamic Prefix Tuning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico. Association for Computational Linguistics. https://aclanthology.org/2024.naacl-long.485/

AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking

Published in ACL 2023 Findings, 2023

In this study, we propose a new task, named unsupervised long-document question answering (ULQA), aiming to generate high-quality long-document QA instances in an unsupervised manner. Besides, we propose AttenWalker, a novel unsupervised method to aggregate and generate answers with long-range dependency so as to construct long-document QA pairs.

Recommended citation: Yuxiang Nie, Heyan Huang, Wei Wei, and Xian-Ling Mao. 2023. AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking. Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada: Association for Computational Linguistics. https://aclanthology.org/2023.findings-acl.862/

Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network

Published in EMNLP 2022, 2022

In this study, we propose Compressive Graph Selector Network (CGSN) to capture the global structure in a compressive and iterative manner.

Recommended citation: Yuxiang Nie, Heyan Huang, Wei Wei, and Xian-Ling Mao. 2022. Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5036–5047, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. https://aclanthology.org/2022.emnlp-main.336/

Unsupervised Question Answering via Answer Diversifying

Published in COLING 2022, 2022

In this study, we propose a method, called DiverseQA, to tackle the problem of diversifying answers in unsupervised question answering.

Recommended citation: Yuxiang Nie, Heyan Huang, Zewen Chi, and Xian-Ling Mao. 2022. Unsupervised Question Answering via Answer Diversifying. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1732–1742, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. https://aclanthology.org/2022.coling-1.149/